Cracked AI Engineering

Llama 3.2 1B Instruct

InferenceOpen Weights

The Llama 3.2 1B Instruct AI model by Inference offers developers a powerful tool with a context window of 16,000 tokens and an output limit of 4,096 tokens. With capabilities for text input and function calling, this model stands out for its open weights and affordable pricing at $0.01/M input and $0.01/M output tokens. Training data cutoff is set for 2023-12, making it a reliable choice for a wide range of AI applications.

Key Specifications

Context Window

16K tokens

Max Output Tokens

4K tokens

Input Pricing

$0.01

per million tokens

Output Pricing

$0.01

per million tokens

Capabilities

  • Text Generation
  • Function Calling

Additional Details

Provider
Inference
Release Date
January 1, 2025
Supported Input Types
text

Compare with Similar Models